© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38789
    Prev
    Next
    INDEX
    Explanations

    Civil War

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of the phrase “Civil War.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瀦
    -2.30
     hadapan
    -2.25
    {
    -2.02
    一方で
    -1.90
     dalamnya
    -1.77
    },[])
    -1.77
    ’
    -1.75
     anderes
    -1.74
    簠
    -1.73
     belakang
    -1.72
    POSITIVE LOGITS
    渽
    2.09
     motto
    2.05
    และ
    2.05
    i
    2.03
     essentielle
    1.90
    他
    1.85
    ・
    1.81
    idemia
    1.81
    TUAL
    1.75
     大
    1.73
    Activations Density 0.006%

    No Known Activations